Wyniki wyszukiwania - Biblioteka Nauki

1

Separation of overlapping bacilli in microscopic digital TB images

100%

Priya E. , Srinivasan S.

|

tom Vol. 35, no. 2

87--99

EN

The sputum smear microscopy based tuberculosis (TB) screening method is a conventional method employed for disease identification. It provides significant benefit to TB burdened communities across the globe; however, there are many challenges faced in processing the sputum smear images. When the smear is thick or uneven the number of overlapping bacilli is more which impedes the diagnosis. The separation of overlapping bacilli is significant without which the results lead to gross errors in identification of the disease causing agent. In this work, separation of overlapping bacilli is carried out by method of concavity (MOC) and is compared with the conventional methods such as multi-phase active contour (MAC) and marker-controlled watershed (MCW). Performance of the methods is evaluated based on the statistical mean quality score of shape descriptors extracted from the separated and existing true bacilli. The shape descriptors employed in this work include geometric features, Hu's, Zernike moments and Fourier descriptors. Results of separated overlapping bacilli demonstrate that MOC performs better than MAC and MCW. It is observed that the statistical mean quality score of the separated bacilli using the proposed MOC shows nearest match with true bacilli. The validation performed with experimental results to that of human annotations highlights the performance of MOC in separating the overlapping bacilli in the sputum smear images.

2

Automated object and image level classification of TB images using support vector neural network classifier

100%

Priya E. , Srinivasan S.

Biocybernetics and Biomedical Engineering

|

2016

|

tom Vol. 36, no. 4

670--678

EN

In this work, digital Tuberculosis (TB) images have been considered for object and image level classification using Multi Layer Perceptron (MLP) neural network activated by Support Vector Machine (SVM) learning algorithm. The sputum smear images are recorded under standard image acquisition protocol. The TB objects which include bacilli and outliers in the considered images are segmented using active contour method. The boundary of the segmented objects is described by fifteen Fourier Descriptors (FDs). The prominent FDs are selected using fuzzy entropy measures. These selected FDs of the TB objects are fed as input to the SVM learning algorithm of the MLP Neural Network (SVNN) and the result is compared with the state-of-the-art approach, Back Propagation Neural Network (BPNN). Results show that the segmentation method identifies the bacilli which retain their shape in-spite of artifacts present in the images. The methodology adopted has significantly enhanced the SVNN accuracy to 91.3% for object and 92.5% for image level classification than BPNN.

3

Estimation of Mold Filling Ability and Volume Deficit Characteristics of Cast Al-Si Alloys

85%

Santhi S. , Vadayar S. , Srinivasan S. , Santhi S. , Vadayar S. , Srinivasan S.

|

tom 19

|

nr 3

4

Estimation of Mold Filling Ability and Volume Deficit Characteristics of Cast Al-Si Alloys

80%

Santhi S. , Vadayar S. , Srinivasan S.

Archives of Foundry Engineering

|

2019

|

tom iss. 3

55--65

EN

Production of defect free castings requires good understanding of casting characteristics like mold filling ability and volume deficit characteristic. Pin test piece with cylindrical cores proposed by Engler and Ellerbrok was used to study the mold filling ability. Volume deficit characteristics experiments were conducted using the method designed by Engler. Alloy composition, Mold coat and Pouring temperature were considered as process parameters for the present study and experimental plan has been taken up through design of experiments. The alloy composition is most significant in influencing the mold filling ability, where as pouring temperature is for volume deficit. The Correlation Co-efficient value obtained is -0.98901 indicating strong a negative relation between mold filling ability and volume deficit characteristics. Negative values indicate a relationship between mold filling ability and volume deficit such that as values for mold filling ability increase, for volume deficit decrease.

5

Enhanced IMC synthesis for tracking control of magnetic levitation system

70%

Elumalai V. K. , Subramanian R. G. , Reddipogu J. S. D. , Srinivasan S. , Agrawal S.

Archives of Electrical Engineering

|

2018

|

tom Vol. 67, nr 2

293–-306

EN

This paper presents an enhanced internal model control (EIMC) scheme for a time-delayed second order unstable process, which is subjected to exogenous disturbance and model variations. Even though the conventional internal model control (IMC) can provide an asymptotic tracking response with desired stability margins, the major limitation of conventional IMC is that it cannot be applied for an unstable system because a small exogenous disturbance can trigger the control signal to grow unbounded. Hence, modifying the conventional IMC structure to guarantee the internal stability, we present an EIMC scheme which can offer better trade-off between setpoint tracking and disturbance rejection characteristics. To improve the load disturbance rejection characteristics and attenuate the effect of sensor noise, we solve the selection of controller gains as an H∞ optimization problem. One of the key aspects of the EIMC scheme is that the robustness of the closed loop system can be tuned via a single tuning parameter. The performance of the EIMC scheme is experimentally assessed on a magnetic levitation plant for reference tracking application. Experimental results substantiate that the EIMC scheme can effectively counteract the inherent time delay in the model and offer precise tracking, even in the presence of exogenous disturbance. Moreover, by comparing the trajectory tracking performance of EIMC with that of the proportional integral velocity (PIV) controller through cumulative power spectral density (CPSD) of the tracking error, we show that the EIMC can offer better low frequency servo response with minimal vibrations.